🤗 AutoTrain Advanced

A modern load testing tool, using Go and JavaScript - https://k6.io

HTTP(S) benchmark tools, testing/debugging, & restAPI (RESTful)

CustomLLM config to leverage watsonx LLMs with continue.dev.

Install automatically IBM Cloudpak for Data using Tekton Pipeline

This project facilitates conversational interaction with any public GitHub repository utilizing advanced technologies such as IBM WatsonX, Langchain, FAISS vector database, and Streamlit.

Chat Complex PDF with Tables Using IBM WatsonX, Langchain and LlamaParser.

Simple implementation of RAG using watsonx.ai, capturing the chat history to keep track of the conversation context and answer follow up questions.

A kubectl plugin supercharged by fzf to create an interactive menu to interact with Kubernetes objects from your terminal.

Red Hat Enterprise Linux AI -- Developer Preview

The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.

A multi-voice TTS system trained with an emphasis on quality

Reasoning in Large Language Models: Papers and Resources, including Chain-of-Thought, Instruction-Tuning and Multimodality.

Starter kit for for modern web developmen with React, Sass, Carbon and Create React App.

Template repository for a Typescript-based Graphql micro-service.

Starting point for creating Java microservice applications running on Spring.

Static documentation site for Cloud Deisgn Patterns learning journey.

Focus on prompting and generating

Command line server and client for webhooks deliveries (and https://smee.io)

Sample cloud-first application with 10 microservices showcasing Kubernetes, Istio, and gRPC.

A reference .NET application implementing an eCommerce site

Mixpost - Self-hosted social media management software (Buffer alternative)

Node-RED node collection for Microsoft Active Directory.

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

LLMPerf is a library for validating and benchmarking LLMs

🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.

Supporting documentation for https://docs.seillama.dev

Get up and running with Llama 3, Mistral, Gemma 2, and other large language models.